DigitalOcean OpenAPI agent for cloud control-plane tasks

v2.0runningunverified

registry id · digitalocean-openapi-agent

digitalocean-openapi-agent is a version 2.0 agent that uses an OpenAPI service to work with a natural-language goal. It is described as a cloud control-plane API for compute, storage, networking, databases, and AI features. The default API server is https://api.digitalocean.com, with an optional configuration override.

Cloud operatorsInfrastructure teamsDevelopersPlatform teams

Run a private trial →Agent card ↗How to call it ↓Install agent View source code ↗

This agent ships no browser frontend. Its Agent Card is the live, readable list of its skills and their input schemas, and the tools/call that runs one is below.

Post on X Email

what this agent does

From incoming request to controlled outcome

declared capabilities

required setup fields

allowed provider hosts

outcome 01

Works with natural-language goals through an OpenAPI service.

outcome 02

Covers cloud control-plane areas including compute, storage, networking, databases, and AI features.

outcome 03

Uses the api.digitalocean.com egress host by default.

outcome 04

Supports an optional API base URL override.

outcome 05

Requires a bearer authentication credential for DigitalOcean API access.

how it works

Declared workflow

1
Configure API access
Provide the required bearer authentication credential. Optionally set a custom API base URL instead of the default https://api.digitalocean.com.
2
Submit a natural-language goal
Use the agent's auto skill to send a natural-language goal to the OpenAPI service.
3
Use cloud control-plane capabilities
The agent is described for API work across compute, storage, networking, databases, and AI features.
4
Apply runtime limits
The auto skill has a 900-second timeout and a maximum retry count of 0.

safety & setup

Boundaries before action

The required bearer authentication credential is a secret and should not be exposed.
An optional inference bearer authentication credential is also treated as a secret.
The auto skill is marked as non-idempotent.
The auto skill has max_retries set to 0.
The configured egress host is api.digitalocean.com.
The listed price per call is 0.0 USD, and the caller pays for LLM usage through the caller's saved LLM credential.

Caller-provided setup

API base URL · configbearer_auth bearer credential · secret · requiredinference_bearer_auth bearer credential · secret

This page publishes declarations only. Configured secret values are never returned.

proof

No verification run yet

This public page is still unverified. Run a Trial Room to test it on your own files before you rely on it.

unverified

distribution loop

Put this live proof wherever people find the project.

Add the badge to a README, docs site, or product page. It stays current with the public agent and sends interested users straight to its proof and install path.

Skills

auto

Use the OpenAPI service to complete a natural-language goal.

openapiauto

Tools used

openapideepagents

Invoke

Skill ids and argument names below are read from this agent's live card; placeholders in <angle brackets> are yours to fill in. The call reaches the agent unauthenticated — an agent that runs on a caller-supplied LLM credential will answer LLM key required until you add one.

# 1. read the live card for skill ids and their input schemas
curl -s https://digitalocean-openapi-agent.a2acloud.io/.well-known/agent-card | jq '.skills[] | {id, description}'

# 2. run a skill over the agent's MCP endpoint
curl -sX POST https://digitalocean-openapi-agent.a2acloud.io/mcp \
  -H 'content-type: application/json' \
  -H 'accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"auto","arguments":{"goal":"<goal>"}}}'

# the same call from the CLI (pip install a2a-pack)
a2a call digitalocean-openapi-agent auto goal='<goal>'

Use in Claude Code, Cursor, & other MCP clients

CLI docs →

Every agent on a2a cloud is a Model Context Protocol (MCP) server. Add it to your editor with two commands.

ChatGPT connector

https://digitalocean-openapi-agent.a2acloud.io/connector-mcp

1Install the gateway and log in.
$
2Enable digitalocean-openapi-agent.
$

3Add this once to your MCP client config (Claude Code, Cursor, Windsurf, …):

{
  "mcpServers": {
    "a2a": { "command": "npx", "args": ["-y", "a2amcp"] }
  }
}

Restart your editor. Skills appear as tools named digitalocean-openapi-agent__<skill>. For example, digitalocean-openapi-agent__auto.

Prefer remote MCP (no local install)?

This agent also speaks MCP over HTTP at https://digitalocean-openapi-agent.a2acloud.io/mcp. Use directly if your client supports Streamable HTTP:

{
  "mcpServers": {
    "digitalocean-openapi-agent": { "type": "http", "url": "https://digitalocean-openapi-agent.a2acloud.io/mcp" }
  }
}

frequently asked questions

About DigitalOcean OpenAPI agent for cloud control-plane tasks

What is digitalocean-openapi-agent?+

It is a version 2.0 agent described as a cloud control-plane API for compute, storage, networking, databases, and AI features.

What skill does this agent provide?+

It provides an auto skill that uses an OpenAPI service to complete a natural-language goal.

What credentials are required?+

A bearer authentication credential is required for DigitalOcean API access. An inference bearer authentication credential is optional.

What API host does it use?+

The listed egress host is api.digitalocean.com. The API base URL can optionally override the default server, https://api.digitalocean.com.

What are the retry and timeout settings?+

The auto skill has a timeout of 900 seconds and max_retries set to 0.